In this class, our TACC Vis Staff will provide and overview on software data visualization as well as training on the use of the Paraview software package to visualize data sets on Stampede2 and Lonestar5.

This course will be available to both in-person and remote attendees via webcast. To register and for more information please visit: https://learn.tacc.utexas.edu/

If you have any questions please contact me at jasona@tacc.utexas.edu

This is the first session in a two part training series that will cover an introduction to the Machine Learning and Big Data processing platforms, programming models as well as libraries and tools that are specifically designed for data-driven analysis.

Each session will be three and a half hours long with approximately three hours of lecture and a half hour of hands-on practice. More details on the specific content covered during each session will be available closer to the session start date.

Local participants are strongly encouraged to attend in-person. To register and for more information please visit: https://learn.tacc.utexas.edu/

If you have any questions please contact me at jasona@tacc.utexas.edu

This is the second session in a two part training series that will cover an introduction to the Machine Learning and Big Data processing platforms, programming models as well as libraries and tools that are specifically designed for data-driven analysis.

Each session will be three and a half hours long with approximately three hours of lecture and a half hour of hands-on practice. More details on the specific content covered during each session will be available closer to the session start date.

Local participants are strongly encouraged to attend in-person. To register and for more information please visit: https://learn.tacc.utexas.edu/

If you have any questions please contact me at jasona@tacc.utexas.edu

The Texas Advanced Computing Center (TACC) will be deploying a new system, Frontera, in mid-2019, with support from the U.S. National Science Foundation as the first phase of the new NSF "Towards a Leadership Class Computing Facility" program.

This webinar will provide a brief overview of the plans for the new system and the broader project that surrounds it, review the architectural design choices made, and discuss the application community that will run on it. The presentation will also provide an update on the current landscape of systems at TACC, how they are used, and how usage is changing. 

The focus of this training will be on programming for advanced architectures on Stampede2. We'll also review the basics of vectorization, discuss the importance of multi-threaded programming, and cover the importance of hybrid programming on manycore architectures.

We will also provide practical information and advice to enable experienced OpenMP and MPI programmers to enhance applications on the manycore architectures. We'll provide recommendations regarding MPI and OpenMP task layout. Optimization methods in multithreading will be covered in depth. An overview of current profiling tools available on Stampede2 will also be presented.

Local participants are strongly encouraged to attend in-person. To register and for more information please visit: https://learn.tacc.utexas.edu/ If you have any questions please contact me at jasona@tacc.utexas.edu

This whole day workshop will instill in the participants fluency in the basic MPI constructs through a series of practical programming exercises. Participants will learn collectives, blocking and non-blocking two-sided communication, and a brief introduction to more advanced topics.

The emphasis of this workshop will be on doing hands-on exercises; there will be little lecturing. This course will be offered to in-person and webcast attendees. Local participants are strongly encouraged to attend in-person. Participants should have a basic command of Unix and a common Unix editor such as Vi or Emacs. Exercises can be done in C, Fortran, or Python.

To register and for more information please visit: https://learn.tacc.utexas.edu/

If you have any questions please contact me at jasona@tacc.utexas.edu

Ranch will be unavailable for an extended maintenance from 5:00 PM (CT) Friday, March 22, through 9:00 AM Monday, March 25, 2019. During this maintenance, the current Ranch archive will transition to a new support infrastructure based on Quantum StorNext hardware and software technology.

Detailed information will be available in a transition guide and an updated Ranch user guide. Both guides are currently under development and will be released when the new system enters production.

After over two decades of operation, the Ranch system has more than 49,000 users. What has been revealed after running Ranch for so long, with so many users, is that continuing to support file storage quotas, implementing a total file count quota, and enforcing explicit data retention periods are the keys to the sustainability of the Ranch archiving environment over the long-term.

In the new environment each user will have a default file quota of 50,000 files and 2TB of storage in their personal directories. Additionally, a "project" directory structure will be implemented to support both shared and user directories that exceed the 2TB per user quota. These "project" directories will be set up only upon PI request, with appropriate file count and file size quotas, a defined retention period, and group permissions allowing shared access.

On March 25, 2019, when users are allowed back onto the Ranch system, all current Ranch user home directories will reside within the new system. These directories will be empty, except for a link (./old_HSM) that will point to the users’ old Ranch directories. Users will have access to their existing data, read-only, through March 31, 2020.

Users are encouraged to migrate the data that they need to keep beyond March 31, 2020 by copying ONLY that data from their existing Ranch directory into their new personal directory. As the file quota of 50,000 files will be in effect for this new directory, using tar or some other methodology will be necessary to keep file count beneath quota for both any migrated data and all new incoming data.

Please submit any questions you may have via the TACC User Portal or the XSEDE User Portal.